R Notebook

options(max.print=1000000)

Warning message:
R graphics engine version 14 is not supported by this version of RStudio. The Plots tab will be disabled until a newer version of RStudio is installed. 

library(readxl)
library(dplyr)

Attaching package: 㤼㸱dplyr㤼㸲

The following objects are masked from 㤼㸱package:stats㤼㸲:

    filter, lag

The following objects are masked from 㤼㸱package:base㤼㸲:

    intersect, setdiff, setequal, union

fileName <- "ANZ synthesised transaction dataset.xlsx"
df <- as.data.frame(read_xlsx(fileName))

Expecting numeric in C3052 / R3052C3: got 'THE DISCOUNT CHEMIST GROUP'Expecting numeric in C4360 / R4360C3: got 'LAND WATER & PLANNING East Melbourne'

# df %>%  rmarkdown::paged_table()
# for (i in seq_along(1:ncol(df)))
# {
#   print(paste("Column ", i, " = ", sum(is.na(df[i]))))
# }
summary(df$amount)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   0.10   16.00   29.00  187.93   53.66 8835.98 

df

#print(df[, 'amount'])

### Average Transaction amount ###
avg_transaction <- mean(df$amount)
{
  plot(avg_transaction, ylab="Average Transaction")
  abline(h=avg_transaction, col='blue')
  legend("topright", legend=paste("Mean: ", round(avg_transaction, digits=2)),
       col="blue", lty=1:2, cex=0.8)
  title(expression(phantom("title (") * "Average Transaction Amount"), col.main = "purple")
}

library(ggdemetra)
#### Finding and pointing Outliers #####
{
  png(filename="outliers.png", width=1350, height=600)
  
  ### Labels
  
  l1 <- labs(x="Names", y="Average Value", title="Outliers", colour='Outliers', size=14)
  
  ### Theme Start
      
  t<- theme(legend.position = c(.98, .98), legend.justification = c("right", "top"),axis.text=element_text(size=12), axis.title=element_text(size=14,face="bold"), 
     legend.title=element_text(colour='red', size=19), axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1, size=12))
  
  ### Geom_Point
  gp <- geom_point(col='blue', size=4)
  
  ### Geom_Text
  gt <- geom_text(aes(label= ifelse(mean_amount_by_names[, 'x'] > quantile(mean_amount_by_names[, 'x'], 0.97) | mean_amount_by_names[, 'x'] < quantile(mean_amount_by_names[, 'x'], 0.01),
     as.character(mean_amount_by_names[, 'Group.1']),'')),hjust=0,vjust=1,size=6,show.legend =T)
  ### Lapply, ggplot
  list_plots <- lapply(mean_amount_by_names[-1], function(data) 
     ggplot(mean_amount_by_names, aes(x= Group.1, y = x, colour='orange', label=mean_amount_by_names[, 'Group.1'])) + t + l1 + gp + gt)
  print(list_plots[[1]])
  dev.off()
}

null device 
          1 

library(lubridate)

Attaching package: 㤼㸱lubridate㤼㸲

The following objects are masked from 㤼㸱package:base㤼㸲:

    date, intersect, setdiff, union

library(dplyr)
library(collapsibleTree)

Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

# df %>% 
#   mutate(months = month(as.POSIXlt(month_extract, format="%d-%m-%Y"))) -> df
# arrange_by_month <- arrange(df, df$months)
# fa <- factor(df$months)
# fa <- factor(fa, levels=c(8, 9, 10))
amount_account_data <- c()
# x<-arrange(df, df$first_name)
#new_data$'Name' <- append(new_data, factor(x$first_name))
account_fact <- factor(x$account)
p <- aggregate(df$amount, list(account_fact), sum)
customer_id_fact <- factor(x$customer_id)
amount_account_data <- append(amount_account_data, p)
z <- c()
for (o in levels(customer_id_fact)){
  z <- append(z, o) #z
}
z <- bind_rows(as.data.frame(z))
amount_account_data <- append(amount_account_data, z)

library(webshot)
z1 <- c()
namesA <- c()
x <- data.frame(x)
for (k in seq_along(1:100)){
  namesA <- filter(x, x$account == amount_account_data$Group.1[k]) 
  z1 <- append(z1, namesA$first_name[1])
}
z1 <- bind_rows(as.data.frame(z1))
amount_account_data <- append(amount_account_data, z1)
amount_account_data

$Group.1
  [1] ACC-1037050564 ACC-1056639002 ACC-1199531521 ACC-1217063613 ACC-1222300524
  [6] ACC-1243371644 ACC-1279356312 ACC-1334819143 ACC-1344825761 ACC-1349834573
 [11] ACC-1424176027 ACC-1438600314 ACC-1443681913 ACC-1496451953 ACC-1516130869
 [16] ACC-1523339231 ACC-154431271  ACC-1598451071 ACC-1608363396 ACC-1650504218
 [21] ACC-1652235822 ACC-1683215619 ACC-1710017148 ACC-1788473090 ACC-1799207998
 [26] ACC-182446574  ACC-1890605467 ACC-1903037542 ACC-1973887809 ACC-1990648130
 [31] ACC-1998563091 ACC-2014856841 ACC-2107684084 ACC-211792489  ACC-2153562714
 [36] ACC-2171593283 ACC-2173390920 ACC-2231965366 ACC-2249586092 ACC-2259139624
 [41] ACC-2265520058 ACC-2270192619 ACC-2305712452 ACC-240804743  ACC-2528867619
 [46] ACC-2615038700 ACC-2650850707 ACC-2673069055 ACC-2674800293 ACC-2681137560
 [51] ACC-2776252858 ACC-2828321672 ACC-2890243754 ACC-2897221629 ACC-2901672282
 [56] ACC-2920611728 ACC-2970114956 ACC-2988263882 ACC-3021093232 ACC-3084464802
 [61] ACC-3100725361 ACC-3233697971 ACC-3317636250 ACC-3326339947 ACC-3481401842
 [66] ACC-3485804958 ACC-3536132544 ACC-354106658  ACC-3541460373 ACC-3689607373
 [71] ACC-3741880913 ACC-37709441   ACC-3771436525 ACC-3827517394 ACC-3879258709
 [76] ACC-3881031190 ACC-38923874   ACC-3941181087 ACC-3954677887 ACC-4059612845
 [81] ACC-4065652575 ACC-414431115  ACC-4163822186 ACC-4258502723 ACC-4274272854
 [86] ACC-4281711154 ACC-53508546   ACC-559365433  ACC-574997646  ACC-588564840 
 [91] ACC-602667573  ACC-721712940  ACC-80388494   ACC-819621312  ACC-847145727 
 [96] ACC-854938045  ACC-90814749   ACC-958000567  ACC-964839203  ACC-966140392 
100 Levels: ACC-1037050564 ACC-1056639002 ACC-1199531521 ... ACC-966140392

$x
  [1]  12150.43  15875.79  35063.36   5840.75  79965.86  23832.75  22324.65  19910.80
  [9]  46827.01   9404.75   8556.48  15898.37  24112.65  21313.13  31584.38  18226.79
 [17]  36117.30 100432.78  29282.43  21740.33  36853.95   5066.66  38064.37   8997.66
 [25]  37250.92  54482.29   5625.67  32829.25  34061.22   5007.11  10111.99   8964.33
 [33]  19825.51  17455.83   5380.52   3559.81  23780.66   7849.89  47811.20   1795.14
 [41]  32162.84   7887.33  24154.79  27828.28  28650.46   1862.70   9047.48  61419.41
 [49]   1465.10  17468.17   7465.84   3236.67  46552.40   3592.86  23939.05  20471.49
 [57]  15824.50  10051.78   3113.29  24373.77  21246.25   7220.04  10203.67   1904.56
 [65]  53327.42  60978.15  21791.81  28154.84  12145.80  43030.76   2868.64  24083.42
 [73]  40490.46  26766.77  34607.58   3978.69  18146.62  17651.01  43153.30  11590.34
 [81]  32875.26  18937.73  31828.85  68420.97   4525.39   2047.24  14308.00  12229.55
 [89]  23970.88  21660.70  19307.04   5206.28  19594.42   8039.26  20102.11  24830.64
 [97]  17530.25  36750.22  17543.92  26432.38

$z
  [1] "CUS-1005756958" "CUS-1117979751" "CUS-1140341822" "CUS-1147642491"
  [5] "CUS-1196156254" "CUS-1220154422" "CUS-1233833708" "CUS-1271030853"
  [9] "CUS-127297539"  "CUS-134193016"  "CUS-134833760"  "CUS-1388323263"
 [13] "CUS-1433879684" "CUS-1462656821" "CUS-1478398256" "CUS-1499065773"
 [17] "CUS-1604596597" "CUS-1609060617" "CUS-1614226872" "CUS-1617121891"
 [21] "CUS-164374203"  "CUS-1646183815" "CUS-1646621553" "CUS-1654129794"
 [25] "CUS-1669695324" "CUS-1739931018" "CUS-1790886359" "CUS-1816693151"
 [29] "CUS-1842679196" "CUS-1892177589" "CUS-1896554896" "CUS-1928710999"
 [33] "CUS-2031327464" "CUS-2059096722" "CUS-2083971310" "CUS-2110742437"
 [37] "CUS-2142601169" "CUS-2155701614" "CUS-2178051368" "CUS-2206365095"
 [41] "CUS-2283904812" "CUS-2317998716" "CUS-2348881191" "CUS-2370108457"
 [45] "CUS-2376382098" "CUS-2484453271" "CUS-2487424745" "CUS-2500783281"
 [49] "CUS-2505971401" "CUS-2599279756" "CUS-261674136"  "CUS-2630892467"
 [53] "CUS-2650223890" "CUS-2663907001" "CUS-2688605418" "CUS-2695611575"
 [57] "CUS-2738291516" "CUS-2819545904" "CUS-2977593493" "CUS-3026014945"
 [61] "CUS-3117610635" "CUS-3129499595" "CUS-3142625864" "CUS-3151318058"
 [65] "CUS-3174332735" "CUS-3180318393" "CUS-3201519139" "CUS-3249305314"
 [69] "CUS-325142416"  "CUS-3255104878" "CUS-326006476"  "CUS-331942311" 
 [73] "CUS-3325710106" "CUS-3336454548" "CUS-3378712515" "CUS-3395687666"
 [77] "CUS-3431016847" "CUS-3462882033" "CUS-3702001629" "CUS-3716701010"
 [81] "CUS-3904958894" "CUS-3989008654" "CUS-4023861240" "CUS-4123612273"
 [85] "CUS-4142663097" "CUS-423725039"  "CUS-443776336"  "CUS-495599312" 
 [89] "CUS-497688347"  "CUS-511326734"  "CUS-51506836"   "CUS-527400765" 
 [93] "CUS-537508723"  "CUS-55310383"   "CUS-586638664"  "CUS-72755508"  
 [97] "CUS-809013380"  "CUS-860700529"  "CUS-880898248"  "CUS-883482547" 

$z1
  [1] "Rhonda"      "Michael"     "Billy"       "Kimberly"    "Michael"    
  [6] "Gregory"     "Tyler"       "Christopher" "Sarah"       "Matthew"    
 [11] "Donald"      "Maria"       "Ryan"        "Ricky"       "Jessica"    
 [16] "Tim"         "Lori"        "Diana"       "Robert"      "Marissa"    
 [21] "Renee"       "Barry"       "Michelle"    "Rachael"     "Susan"      
 [26] "Tonya"       "Alexander"   "Jeffrey"     "Antonio"     "Kaitlyn"    
 [31] "David"       "Patrick"     "Richard"     "Jacqueline"  "Linda"      
 [36] "Fernando"    "Luis"        "Linda"       "Edward"      "Cindy"      
 [41] "Catherine"   "Darren"      "Debra"       "Kenneth"     "Abigail"    
 [46] "Emily"       "Brian"       "Richard"     "Elizabeth"   "Nathaniel"  
 [51] "Kristin"     "Stephanie"   "Joseph"      "Scott"       "Daniel"     
 [56] "Tyler"       "Robert"      "Michael"     "Melissa"     "Susan"      
 [61] "Ronald"      "Robin"       "Kenneth"     "Eric"        "Tiffany"    
 [66] "Jessica"     "Heather"     "Christine"   "Jeffrey"     "Virginia"   
 [71] "Ashley"      "Charles"     "Derek"       "Craig"       "Natasha"    
 [76] "Richard"     "Ryan"        "Paul"        "Ruth"        "Jonathan"   
 [81] "Lucas"       "Amy"         "Karen"       "Kimberly"    "Timothy"    
 [86] "Eric"        "Kimberly"    "Mary"        "Mackenzie"   "Isaiah"     
 [91] "Michael"     "Andrew"      "Dustin"      "Michele"     "Michael"    
 [96] "James"       "Christopher" "Sandra"      "Michael"     "Joseph"     

amount_account_data <- as.data.frame(amount_account_data)
widgetToPng <- function(widget, file = "widget.png",  ...) {
  temp <- tempfile(fileext = ".html")
  file <- R.utils::getAbsolutePath(file)
  htmlwidgets::saveWidget(widget, temp)
  webshot(
    temp, file,
    selector = "#htmlwidget_container",
    zoom = 2,
    delay = 0.5,
    ...
  )
}
widgetToPng(
  collapsibleTreeSummary(
  amount_account_data,
  hierarchy = c("z1", "Group.1", "z", 'x'),
  width = 1000,
  height=1000,
  fill="lightsteelblue",
  root = "Customer Details",
  zoomable = FALSE
),
  "CustomerDetailsTree.png"
)

Error in collapsibleTreeSummary(amount_account_data, hierarchy = c("z1",  : 
  fill must be a function